Low Complexity FPGA Implementation of Emotion Detection for Autistic Children

Abstract

Many autistic children have impairment in understanding other people's emotions which hinder their interpersonal communication. A real-time portable emotion detection system will aid such children to interact with the external world easily by them to understand facial emotions during their face to face communication. In this paper we propose a portable low complexity emotion detector using principal component analysis. The Eigen values are obtained using power-deflation iteration method and the proposed architecture optimizes the calculation by using only the required number of selective Eigen values called as Eigen range rather than finding all the Eigen values and vectors. The proposed emotion recognizer architecture is implemented on Virtex 7 XC7VX330T FFG1761-3 FPGA. We achieved 82.3 % detection accuracy for a wordlength of 8 bits.